Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/superplan-md/superplan-plugin/superplan-plannpx skills add superplan-md/superplan-plugin --skill superplan-plangit clone --depth 1 https://github.com/superplan-md/superplan-pluginWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00029 | $0.01235 |
| Opus 5 | $0.00015 | $0.00617 |
| Sonnet 5 | $0.00006 | $0.00247 |
| Haiku 4.5 | $0.00003 | $0.00123 |
Grade A, and why
superplan-plan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Plans
Overview
Turn an understood target into the current execution path.
In Superplan, this means writing or updating the current change plan through the CLI, while keeping graph truth, spec truth, and task-contract truth distinct.
Trigger
Use when:
- the direction is clear enough that sequencing, coordination, or execution path is now the main problem
- approved design exists and the next need is executable planning
- work needs durable trajectory before execution starts
Core Rules
- write the current path, not a fake immutable master plan
- use
superplan change plan set <change-slug> --stdin --jsonfor sequencing, dependency logic, and execution strategy - derive tasks only as far as they are honestly shapeable now
- keep plans bite-sized and execution-oriented
- use exact artifact targets, verification paths, and handoffs rather than vague prose
- pull in
.superplan/context/,.superplan/decisions.md, and.superplan/gotchas.mdwhen they materially affect the path - keep specs and plans distinct: specs capture target truth, plans capture trajectory
- when the plan already defines two or more new task contracts that are ready to author now, prefer handing off one
superplan task scaffold batch <change-slug> --stdin --jsonscaffold step instead of repeatedsuperplan task scaffold newcalls
Public-Facing Planning Rules
Make the useful reasoning visible to the user without narrating Superplan ceremony.
- This skill runs in
planning mode. - lead with a brief read on what the user appears to want and what makes that intent matter
- state a recommendation, not just a neutral recap
- when multiple viable paths exist, present
2-3concrete approaches with trade-offs before locking into one - explain why the recommended path is better for this repo or request right now
- surface real opinions, risks, and sequencing judgments instead of flattening them into generic intent summaries
- keep internal phase names, command choreography, and storage details out of the foreground unless they directly affect the user's decision
- do not hide behind control-plane terseness here; the user should be able to see the approaches, recommendation, trade-offs, and execution path clearly
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 138 lines · 29 tokens per session scan A b99a7696fe4f
superplan-plan is a skill published in the GitHub repository superplan-md/superplan-plugin (72 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 1,235 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
evolve
Research-driven multi-cycle improvement director. Forms causal hypotheses about why scores are low, validates them with scout agents before attacking, dispatches axis-parallel fleet attacks, extracts transferable patterns, and runs indefinitely within a budget envelope. Accumulates a persistent belief model and…
improve
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
setup
First-run experience for the harness. Three modes: Recommended (guided, 3 min), Full Tour (guided + skill walkthrough, 8 min), and Express (zero questions, 30 sec). Installs hooks first, detects stack, configures harness.json, runs a live demo on real code, and prints a reference card.
ascii-diagram
Generate perfectly aligned ASCII diagrams — architecture, flow, sequence, box-and-arrow. Uses a programmatic character-grid approach so alignment is guaranteed by math, not token prediction. Includes post-render verification.
research
Focused research investigations. Converts questions into structured findings with confidence levels and source citations. Single agent by default; with --parallel (or when the question decomposes into 3+ independent angles) it spawns scout agents whose findings are compressed into a unified brief. Does not make…
triage
GitHub issue and PR investigator. Pulls open issues/PRs, classifies them, searches the codebase for root cause or reviews contributed code, proposes fixes with file:line references, and optionally implements fixes. Use for investigating GitHub issues and reviewing PRs; do NOT use for general code review unrelated to…